Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 13801v1 Announce Type: new Abstract: Neural responses in cortex exhibit substantial trial-to-trial variability in response to repeated stimuli, while peripheral sensory neurons respond far more consistently, leading many to wonder whether stochasticity may carry meaning.
arXiv:2606. 12923v2 Announce Type: replace-cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects.
arXiv:2606. 14040v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are typically trained to reconstruct the \textbf{entire} residual stream through a sparse dictionary, implicitly assuming that all activation content is amenable to sparse, monosemantic decomposition.
arXiv:2602. 23638v3 Announce Type: replace-cross Abstract: Federated LoRA provides a communication-efficient mechanism for fine-tuning large language models on decentralized data.
arXiv:2510. 02695v3 Announce Type: replace-cross Abstract: In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) is attractive only if policies achieve high returns without catastrophic lower-tail risk.
arXiv:2605. 09420v2 Announce Type: replace-cross Abstract: In this study, we tackle Generalized Category Discovery (GCD) via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidirectional knowledge transfer.
arXiv:2606. 14608v1 Announce Type: cross Abstract: Survival prediction plays a central role for healthcare providers and clinical researchers.
arXiv:2606. 14488v1 Announce Type: cross Abstract: Recent finite-time analyses of nonlinear two-time-scale stochastic approximation show that under contractive assumptions the slow iterate $Y_k$ with stepsizes $\beta_k=\Theta(k^{-1})$ and $\alpha_k=\Theta(k^{-a})$, $a\in(1/2,1)$, generally satisfies a mean-square rate of order $k^{-a}$; decoupled $k^{-1}$ rates require strong local linearity.
arXiv:2606. 14594v1 Announce Type: cross Abstract: AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision.
arXiv:2605. 11558v2 Announce Type: replace Abstract: Activation functions play a central role in neural networks by shaping internal representations.
arXiv:2606. 13709v1 Announce Type: cross Abstract: We study controlled post-training refusal suppression in routed MoE and hybrid-MoE foundation models, aiming to increase non-refusal target-response behavior while preserving general capability under a compact intervention footprint.
arXiv:2606. 14466v1 Announce Type: cross Abstract: This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection.
arXiv:2512. 23847v2 Announce Type: replace-cross Abstract: We develop a statistical procedure to detect lookahead bias in economic forecasts generated by large language models (LLMs).
arXiv:2606. 13794v1 Announce Type: cross Abstract: Nonlinear dynamics and the strong couplings that arise between multiple effectors undermine the assumptions behind conventional, linear control allocation techniques.
arXiv:2606. 14123v1 Announce Type: cross Abstract: Deployed knowledge-tracing models are typically frozen after training, yet systematic per-item logit bias arises, from limited per-item expressivity in backbone architectures and from post-deployment shifts in item properties, degrading prediction quality.
arXiv:2606. 14117v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly evaluated for bias using adaptations of human psychological paradigms, yet methodological limitations-particularly the conflation of refusal behavior with task performance-have hindered clear interpretation.
arXiv:2606. 14120v1 Announce Type: cross Abstract: Auditory attention decoding (AAD) aims to infer the attended speaker from neural responses in multi-speaker acoustic environments and is a key problem for neuro-steered hearing systems.
arXiv:2606. 14648v1 Announce Type: new Abstract: Robust machine learning and optimization rely on the uncertainty model choice.
arXiv:2606. 14686v1 Announce Type: cross Abstract: Globally, cotton is a highly economically beneficial crop, as the textile industry heavily depends on it.
arXiv:2510. 01663v2 Announce Type: replace-cross Abstract: For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy.